Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to age restrictions and eligibility criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uitka
    -0.16
    urch
    -0.16
    uard
    -0.15
    efon
    -0.15
    apr
    -0.15
    ASSES
    -0.15
    лив
    -0.15
    akat
    -0.14
    acades
    -0.14
    uce
    -0.14
    POSITIVE LOGITS
     adult
    0.35
     adults
    0.34
     age
    0.32
     Adults
    0.29
    adult
    0.29
    Adult
    0.28
     Adult
    0.26
     Age
    0.24
     adulthood
    0.23
    -age
    0.22
    Act Density 0.056%

    No Known Activations